Class swarmauri_standard.llms.HyperbolicModel.HyperbolicModel

swarmauri_standard.llms.HyperbolicModel.HyperbolicModel

HyperbolicModel(**data)

Bases: LLMBase

HyperbolicModel class for interacting with the Hyperbolic AI language models API.

ATTRIBUTE	DESCRIPTION
api_key	API key for authenticating requests to the Hyperbolic API. TYPE: str
allowed_models	List of allowed model names that can be used. TYPE: List[str]
name	The default model name to use for predictions. TYPE: str
type	The type identifier for this class. TYPE: Literal['HyperbolicModel']

Link to Allowed Models: https://app.hyperbolic.xyz/models Link to API KEYS: https://app.hyperbolic.xyz/settings

Initialize the HyperbolicModel class with the provided data.

PARAMETER	DESCRIPTION
**data	Arbitrary keyword arguments containing initialization data. TYPE: Dict[str, Any] DEFAULT: {}

Source code in swarmauri_standard/llms/HyperbolicModel.py

def __init__(self, **data: Dict[str, Any]) -> None:
    """
    Initialize the HyperbolicModel class with the provided data.

    Args:
        **data (Dict[str, Any]): Arbitrary keyword arguments containing initialization data.
    """
    super().__init__(**data)
    self._headers = {
        "Authorization": f"Bearer {self.api_key.get_secret_value()}",
        "Content-Type": "application/json",
        "Accept": "application/json",
    }
    self._client = httpx.Client(
        headers=self._headers,
        base_url=self._BASE_URL,
        timeout=self.timeout,
    )

api_key instance-attribute

api_key

allowed_models class-attribute instance-attribute

allowed_models = [
    "openai/gpt-oss-120b",
    "openai/gpt-oss-20b",
    "Qwen/Qwen3-Coder-480B-A35B-Instruct",
    "Qwen/Qwen3-235B-A22B-Instruct-2507",
    "moonshotai/Kimi-K2-Instruct",
    "deepseek-ai/DeepSeek-R1-0528",
    "Qwen/Qwen3-235B-A22B",
    "deepseek-ai/DeepSeek-V3-0324",
    "meta-llama/Meta-Llama-3-70B-Instruct",
    "meta-llama/Meta-Llama-3.1-70B-Instruct",
    "meta-llama/Meta-Llama-3.1-8B-Instruct",
    "meta-llama/Meta-Llama-3.1-405B-FP8",
    "meta-llama/Meta-Llama-3.1-405B-Instruct",
]

name class-attribute instance-attribute

name = 'meta-llama/Meta-Llama-3-70B-Instruct'

type class-attribute instance-attribute

type = 'HyperbolicModel'

timeout class-attribute instance-attribute

timeout = 600.0

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="allow", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

resource class-attribute instance-attribute

resource = Field(default=LLM.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

include_usage class-attribute instance-attribute

include_usage = True

BASE_URL class-attribute instance-attribute

BASE_URL = None

get_allowed_models

get_allowed_models()

Get a list of allowed models for the Hyperbolic API.

RETURNS	DESCRIPTION
List[str]	List[str]: List of allowed model names.

Source code in swarmauri_standard/llms/HyperbolicModel.py

@retry_on_status_codes((429, 529), max_retries=1)
def get_allowed_models(self) -> List[str]:
    """
    Get a list of allowed models for the Hyperbolic API.

    Returns:
        List[str]: List of allowed model names.
    """
    response = self._client.get("models")
    response.raise_for_status()
    response_data = response.json()

    chat_models = [
        model["id"] for model in response_data["data"] if model["supports_chat"]
    ]
    return chat_models

predict

predict(
    conversation,
    temperature=0.7,
    max_tokens=None,
    top_p=1.0,
    top_k=-1,
    enable_json=False,
    stop=None,
)

Generates a response from the model based on the given conversation.

PARAMETER	DESCRIPTION
conversation	Conversation object with message history. TYPE: Conversation
temperature	Sampling temperature for response diversity. TYPE: float DEFAULT: 0.7
max_tokens	Maximum tokens for the model's response. TYPE: Optional[int] DEFAULT: None
top_p	Cumulative probability for nucleus sampling. TYPE: float DEFAULT: 1.0
top_k	Maximum number of tokens to consider at each step. TYPE: int DEFAULT: -1
enable_json	Whether to format the response as JSON. TYPE: bool DEFAULT: False
stop	List of stop sequences for response termination. TYPE: Optional[List[str]] DEFAULT: None

RETURNS	DESCRIPTION
Conversation	Updated conversation with the model's response. TYPE: Conversation

Source code in swarmauri_standard/llms/HyperbolicModel.py

@retry_on_status_codes((429, 529), max_retries=1)
def predict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: Optional[int] = None,
    top_p: float = 1.0,
    top_k: int = -1,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> Conversation:
    """
    Generates a response from the model based on the given conversation.

    Args:
        conversation (Conversation): Conversation object with message history.
        temperature (float): Sampling temperature for response diversity.
        max_tokens (Optional[int]): Maximum tokens for the model's response.
        top_p (float): Cumulative probability for nucleus sampling.
        top_k (int): Maximum number of tokens to consider at each step.
        enable_json (bool): Whether to format the response as JSON.
        stop (Optional[List[str]]): List of stop sequences for response termination.

    Returns:
        Conversation: Updated conversation with the model's response.
    """
    formatted_messages = self._format_messages(conversation.history)
    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "top_p": top_p,
        "top_k": top_k,
        "stream": False,
    }

    if max_tokens is not None:
        payload["max_tokens"] = max_tokens
    if stop is not None:
        payload["stop"] = stop

    with DurationManager() as promt_timer:
        response = self._client.post("chat/completions", json=payload)
        response.raise_for_status()

    response_data = response.json()
    message_content = response_data["choices"][0]["message"]["content"]
    usage_data = response_data.get("usage", {})

    if self.include_usage and usage_data:
        usage = self._prepare_usage_data(usage_data, promt_timer.duration)
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))
    return conversation

apredict async

apredict(
    conversation,
    temperature=0.7,
    max_tokens=None,
    top_p=1.0,
    top_k=-1,
    enable_json=False,
    stop=None,
)

Async method to generate a response from the model based on the given conversation.

Args are same as predict method.

Source code in swarmauri_standard/llms/HyperbolicModel.py

@retry_on_status_codes((429, 529), max_retries=1)
async def apredict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: Optional[int] = None,
    top_p: float = 1.0,
    top_k: int = -1,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> Conversation:
    """
    Async method to generate a response from the model based on the given conversation.

    Args are same as predict method.
    """
    formatted_messages = self._format_messages(conversation.history)
    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "top_p": top_p,
        "top_k": top_k,
        "stream": False,
    }

    if max_tokens is not None:
        payload["max_tokens"] = max_tokens
    if stop is not None:
        payload["stop"] = stop

    with DurationManager() as promt_timer:
        async with httpx.AsyncClient(timeout=self.timeout) as client:
            response = await client.post(
                f"{self._BASE_URL}chat/completions",
                headers=self._headers,
                json=payload,
            )
            response.raise_for_status()

    response_data = response.json()
    message_content = response_data["choices"][0]["message"]["content"]
    usage_data = response_data.get("usage", {})

    if self.include_usage and usage_data:
        usage = self._prepare_usage_data(usage_data, promt_timer.duration)
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))
    return conversation

stream

stream(
    conversation,
    temperature=0.7,
    max_tokens=None,
    top_p=1.0,
    top_k=-1,
    enable_json=False,
    stop=None,
)

Streams response text from the model in real-time.

Args are same as predict method.

YIELDS	DESCRIPTION
str	Partial response content from the model. TYPE:: str

Source code in swarmauri_standard/llms/HyperbolicModel.py

@retry_on_status_codes((429, 529), max_retries=1)
def stream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: Optional[int] = None,
    top_p: float = 1.0,
    top_k: int = -1,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> Generator[str, None, None]:
    """
    Streams response text from the model in real-time.

    Args are same as predict method.

    Yields:
        str: Partial response content from the model.
    """
    formatted_messages = self._format_messages(conversation.history)
    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "top_p": top_p,
        "top_k": top_k,
        "stream": True,
    }

    if max_tokens is not None:
        payload["max_tokens"] = max_tokens
    if stop is not None:
        payload["stop"] = stop

    with DurationManager() as promt_timer:
        response = self._client.post("chat/completions", json=payload)
        response.raise_for_status()

    message_content = ""
    usage_data = {}
    with DurationManager() as completion_timer:
        for line in response.iter_lines():
            json_str = line.replace("data: ", "")
            try:
                if json_str:
                    chunk = json.loads(json_str)
                    if chunk["choices"] and chunk["choices"][0]["delta"]:
                        delta = chunk["choices"][0]["delta"]["content"]
                        message_content += delta
                        yield delta
                    if "usage" in chunk and chunk["usage"] is not None:
                        usage_data = chunk["usage"]
            except json.JSONDecodeError:
                pass
    if self.include_usage and usage_data:
        usage = self._prepare_usage_data(
            usage_data, promt_timer.duration, completion_timer.duration
        )
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))

astream async

astream(
    conversation,
    temperature=0.7,
    max_tokens=None,
    top_p=1.0,
    top_k=-1,
    enable_json=False,
    stop=None,
)

Async generator that streams response text from the model in real-time.

Args are same as predict method.

YIELDS	DESCRIPTION
str	Partial response content from the model. TYPE:: AsyncGenerator[str, None]

Source code in swarmauri_standard/llms/HyperbolicModel.py

@retry_on_status_codes((429, 529), max_retries=1)
async def astream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: Optional[int] = None,
    top_p: float = 1.0,
    top_k: int = -1,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> AsyncGenerator[str, None]:
    """
    Async generator that streams response text from the model in real-time.

    Args are same as predict method.

    Yields:
        str: Partial response content from the model.
    """
    formatted_messages = self._format_messages(conversation.history)
    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "top_p": top_p,
        "top_k": top_k,
        "stream": True,
    }

    if max_tokens is not None:
        payload["max_tokens"] = max_tokens
    if stop is not None:
        payload["stop"] = stop

    with DurationManager() as promt_timer:
        async with httpx.AsyncClient(timeout=self.timeout) as client:
            response = await client.post(
                f"{self._BASE_URL}chat/completions",
                headers=self._headers,
                json=payload,
            )
            response.raise_for_status()

    message_content = ""
    usage_data = {}
    with DurationManager() as completion_timer:
        async for line in response.aiter_lines():
            json_str = line.replace("data: ", "")
            try:
                if json_str:
                    chunk = json.loads(json_str)
                    if chunk["choices"] and chunk["choices"][0]["delta"]:
                        delta = chunk["choices"][0]["delta"]["content"]
                        message_content += delta
                        yield delta
                    if "usage" in chunk and chunk["usage"] is not None:
                        usage_data = chunk["usage"]
            except json.JSONDecodeError:
                pass

    if self.include_usage and usage_data:
        usage = self._prepare_usage_data(
            usage_data, promt_timer.duration, completion_timer.duration
        )
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))

batch

batch(
    conversations,
    temperature=0.7,
    max_tokens=None,
    top_p=1.0,
    top_k=-1,
    enable_json=False,
    stop=None,
)

Processes a batch of conversations and generates responses for each sequentially.

Args are same as predict method.

Source code in swarmauri_standard/llms/HyperbolicModel.py

def batch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: Optional[int] = None,
    top_p: float = 1.0,
    top_k: int = -1,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> List[Conversation]:
    """
    Processes a batch of conversations and generates responses for each sequentially.

    Args are same as predict method.
    """
    results = []
    for conversation in conversations:
        result_conversation = self.predict(
            conversation,
            temperature=temperature,
            max_tokens=max_tokens,
            top_p=top_p,
            top_k=top_k,
            enable_json=enable_json,
            stop=stop,
        )
        results.append(result_conversation)
    return results

abatch async

abatch(
    conversations,
    temperature=0.7,
    max_tokens=None,
    top_p=1.0,
    top_k=-1,
    enable_json=False,
    stop=None,
    max_concurrent=5,
)

Async method for processing a batch of conversations concurrently.

Args are same as predict method, with additional arg: max_concurrent (int): Maximum number of concurrent requests.

Source code in swarmauri_standard/llms/HyperbolicModel.py

async def abatch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: Optional[int] = None,
    top_p: float = 1.0,
    top_k: int = -1,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
    max_concurrent=5,
) -> List[Conversation]:
    """
    Async method for processing a batch of conversations concurrently.

    Args are same as predict method, with additional arg:
        max_concurrent (int): Maximum number of concurrent requests.
    """
    semaphore = asyncio.Semaphore(max_concurrent)

    async def process_conversation(conv: Conversation) -> Conversation:
        async with semaphore:
            return await self.apredict(
                conv,
                temperature=temperature,
                max_tokens=max_tokens,
                top_p=top_p,
                top_k=top_k,
                enable_json=enable_json,
                stop=stop,
            )

    tasks = [process_conversation(conv) for conv in conversations]
    return await asyncio.gather(*tasks)

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS	DESCRIPTION
Callable	A decorator function that registers the model class. TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER	DESCRIPTION
resource_type	The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used. TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None
type_name	An optional custom type name for the subtype. TYPE: Optional[str] DEFAULT: None

RETURNS	DESCRIPTION
Callable	A decorator function that registers the subtype. TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py

@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py

def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py

@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py

def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py

def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger

add_allowed_model

add_allowed_model(model)

Add a new model to the list of allowed models.

RAISES	DESCRIPTION
ValueError	If the model is already in the allowed models list.

Source code in swarmauri_base/llms/LLMBase.py

def add_allowed_model(self, model: str) -> None:
    """
    Add a new model to the list of allowed models.

    Raises:
        ValueError: If the model is already in the allowed models list.
    """
    if model in self.allowed_models:
        raise ValueError(f"Model '{model}' is already allowed.")
    self.allowed_models.append(model)

remove_allowed_model

remove_allowed_model(model)

Remove a model from the list of allowed models.

RAISES	DESCRIPTION
ValueError	If the model is not in the allowed models list.

Source code in swarmauri_base/llms/LLMBase.py

def remove_allowed_model(self, model: str) -> None:
    """
    Remove a model from the list of allowed models.

    Raises:
        ValueError: If the model is not in the allowed models list.
    """
    if model not in self.allowed_models:
        raise ValueError(f"Model '{model}' is not in the allowed models list.")
    self.allowed_models.remove(model)